LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents
cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/DongshengXiao/LLM-Parkinsonism-Solutions
Terminology
Sources
- ReAct: Synergizing Reasoning and Acting in Language Models
- Training language models to follow instructions with human feedback
- AI Agents That Matter
- BAGEN: Are LLM Agents Budget-Aware?
- When Agents Do Not Stop: Uncovering Infinite Agentic Loops in LLM Agents
- When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops
- When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMs
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection